AI Paper Atlas

Research map / 3D vision / Human pose estimation

Dynamical Pose Estimation

Heng Yang, Chris Doran, Jean-Jacques Slotine

ICCV 2021 · 3D vision › Human pose estimation · approach: Category-level pose estimation · 10 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add EscapeMinimum scheme (ablation)DAMP · Absolute pose estimation (N=100)success rate (%): 99.8 -> 100Improved
add EscapeMinimum scheme (ablation)DAMP · Absolute pose estimation (N=50, N=200)success rate (%): 100 -> 100No clear effect
add EscapeMinimum scheme (ablation)DAMP · FG3DCar category APE (300 images)images failed: fails on 6 out of the 300 images -> succeeds on all 300 imagesImproved
use DAMP instead of SDR certifiable solver for primitive registrationprimitive registration · random primitive registration (150 primitives)runtime: about 10 times fasterImproved
use DAMP instead of SDR for primitive registrationprimitive registration · random primitive registration (150 primitives)rotation errorNo clear effect
use DAMP instead of SVD for 3D point cloud registrationpoint cloud registration · Point cloud registration (N=100)runtime: 6.3 millisecondsHurt
use DAMP instead of Shape* for category APEcategory APE · FG3DCar category APE (300 images)runtime: 20 seconds vs about 1 minuteImproved

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy